Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to explain or condemn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    о
    0.43
    ucht
    0.42
    ាទ
    0.42
    Н
    0.41
    ৬
    0.41
     கட்ட
    0.40
    ranial
    0.40
    ६
    0.39
    ۶
    0.39
    Л
    0.39
    POSITIVE LOGITS
     spieg
    0.40
     boroughs
    0.40
     উড়ে
    0.40
     অঞ্জু
    0.39
    詫
    0.38
     explaining
    0.38
    ändert
    0.38
     समझाया
    0.37
    স্থিত
    0.37
    ަނ
    0.37
    Act Density 0.001%

    No Known Activations